Large Language Models (LLMs) have become pervasive in everyday life, yet
their inner workings remain opaque. While scholarly efforts have demonstrated
LLMs' propensity to reproduce biases in their training data, they have
primarily focused on the association of social groups with stereotypic
attributes. In this paper, we extend this line of inquiry to investigate a bias
akin to the social-psychological phenomenon where socially dominant groups are
perceived to be less homogeneous than socially subordinate groups as it is
reproduced by LLMs. We had ChatGPT, a state-of-the-art LLM, generate a
diversity of texts about intersectional group identities and compared text
homogeneity. We consistently find that LLMs portray African, Asian, and
Hispanic Americans as more homogeneous than White Americans. They also portray
women as more homogeneous than men, but these differences are small. Finally,
we find that the effect of gender differs across racial/ethnic groups such that
the effect of gender is consistent within African and Hispanic Americans but
not within Asian and White Americans. We speculate possible sources of this
bias in LLMs and posit that the bias has the potential to amplify biases in
future LLM training and to reinforce stereotypes.

大型语言模型经常用于日常生活，但其内部机制仍然不透明。本文将研究 LLMs 中存在的偏见，特别是与社会群体的刻板属性相关的偏见，并扩展研究范围，探究 LLMs 中的另一种偏见，即社会优势群体相对于社会从属群体更具异质性的现象。本研究使用 ChatGPT，一个最先进的 LLM，生成了关于交叉群体身份的多样化文本，并比较了文本的同质性。我们一致发现，LLMs 将非洲裔、亚洲裔和拉美裔美国人描绘为比白人更具同质性。他们还描绘女性比男性更具同质性，但这些差异很小。最后，我们发现性别的影响在种族 / 民族群体中存在差异，即在非洲裔和拉美裔美国人中性别的影响是一致的，但在亚洲裔和白人中不一致。我们对 LLMs 中这种偏见的可能来源进行了推测，并指出这种偏见有可能放大未来 LLM 训练中的偏见并强化刻板印象。